DetectiveRedasers at ArAIEval Shared Task: Leveraging Transformer Ensembles for Arabic Deception Detection
Year: 2023
Type: conference-paper
Abstract: This paper outlines a methodology aimed at combating disinformation in Arabic social media, a strategy that secured a first-place finish in tasks 2A and 2B at the ArAIEval shared task during the ArabicNLP 2023 conference.Our team developed a hyperparameter-optimized pipeline centered around BERT-based models for the Arabic language, enhanced by a soft-voting ensemble strategy.Subsequent evaluation on the test dataset reveals that ensembles, although generally resilient, do not always outperform individual models.The primary contributions of this paper are its multifaceted strategy, which led to winning solutions for both binary (2A) and multiclass (2B) disinformation classification tasks.
Authors: Bryan Tuck, Fatima Qachfar, Dainis Boumber, Rakesh Verma
Institution: University of Houston
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
Awards: G2057110230, Scholarships for Service: Increasing Talented Trus, G6523399184, REU Site: Undergraduate Research Experience in Frontiers of Data-Driven Computing, EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Inoculation vs. education: the role of real time alerts and end-user overconfidence, G7452299184, G8876996369
OpenAlex ID: W4389518350